merlimat commented on code in PR #22054:
URL: https://github.com/apache/pulsar/pull/22054#discussion_r1491451784
##########
docker/pulsar/Dockerfile:
##########
@@ -26,82 +26,83 @@ ADD ${PULSAR_TARBALL} /
RUN mv /apache-pulsar-* /pulsar
RUN rm -rf /pulsar/bin/*.cmd
-COPY scripts/apply-config-from-env.py /pulsar/bin
-COPY scripts/apply-config-from-env-with-prefix.py /pulsar/bin
-COPY scripts/gen-yml-from-env.py /pulsar/bin
-COPY scripts/generate-zookeeper-config.sh /pulsar/bin
-COPY scripts/pulsar-zookeeper-ruok.sh /pulsar/bin
-COPY scripts/watch-znode.py /pulsar/bin
-COPY scripts/install-pulsar-client.sh /pulsar/bin
+COPY scripts/* /pulsar/bin/
# The final image needs to give the root group sufficient permission for
Pulsar components
# to write to specific directories within /pulsar
# The file permissions are preserved when copying files from this builder
image to the target image.
-RUN for SUBDIRECTORY in conf data download logs; do \
+RUN for SUBDIRECTORY in conf data download logs instances/deps; do \
[ -d /pulsar/$SUBDIRECTORY ] || mkdir /pulsar/$SUBDIRECTORY; \
- chmod -R g+w /pulsar/$SUBDIRECTORY; \
+ chmod -R g+rwx /pulsar/$SUBDIRECTORY; \
done
-### Create 2nd stage from Ubuntu image
-### and add OpenJDK and Python dependencies (for Pulsar functions)
+RUN chmod -R g+rx /pulsar/bin
+RUN chmod -R o+rx /pulsar
-FROM ubuntu:22.04
+## Create 2nd stage to build the Python dependencies
+## Since it needs to have GCC available, we're doing it in a different layer
+FROM alpine:3.19 AS python-deps
+
+RUN apk add --no-cache \
+ bash \
+ python3-dev \
+ g++ \
+ musl-dev \
+ libffi-dev \
+ py3-pip \
+ py3-grpcio \
+ py3-yaml
+
+RUN pip3 install --break-system-packages \
+ kazoo
+
+ARG PULSAR_CLIENT_PYTHON_VERSION
+RUN pip3 install --break-system-packages \
+ pulsar-client[all]==${PULSAR_CLIENT_PYTHON_VERSION}
-ARG DEBIAN_FRONTEND=noninteractive
-ARG UBUNTU_MIRROR=http://archive.ubuntu.com/ubuntu/
-ARG UBUNTU_SECURITY_MIRROR=http://security.ubuntu.com/ubuntu/
-ARG DEFAULT_USERNAME=pulsar
-ARG JDK_MAJOR_VERSION=17
+
+## Create final stage from Alpine image
+## and add OpenJDK and Python dependencies (for Pulsar functions)
+FROM alpine:3.19.1
+ENV LANG C.UTF-8
# Install some utilities
-RUN sed -i -e
"s|http://archive\.ubuntu\.com/ubuntu/|${UBUNTU_MIRROR:-http://archive.ubuntu.com/ubuntu/}|g"
\
- -e
"s|http://security\.ubuntu\.com/ubuntu/|${UBUNTU_SECURITY_MIRROR:-http://security.ubuntu.com/ubuntu/}|g"
/etc/apt/sources.list \
- && echo 'Acquire::http::Timeout
"30";\nAcquire::http::ConnectionAttemptDelayMsec
"2000";\nAcquire::https::Timeout
"30";\nAcquire::https::ConnectionAttemptDelayMsec
"2000";\nAcquire::ftp::Timeout "30";\nAcquire::ftp::ConnectionAttemptDelayMsec
"2000";\nAcquire::Retries "15";' > /etc/apt/apt.conf.d/99timeout_and_retries \
- && apt-get update \
- && apt-get -y dist-upgrade \
- && apt-get -y install netcat dnsutils less procps iputils-ping \
- curl ca-certificates wget apt-transport-https \
- && apt-get -y install --no-install-recommends python3 python3-kazoo
python3-pip
-
-# Install Eclipse Temurin Package
-RUN mkdir -p /etc/apt/keyrings \
- && wget -O - https://packages.adoptium.net/artifactory/api/gpg/key/public
| tee /etc/apt/keyrings/adoptium.asc \
- && echo "deb [signed-by=/etc/apt/keyrings/adoptium.asc]
https://packages.adoptium.net/artifactory/deb $(awk -F=
'/^VERSION_CODENAME/{print$2}' /etc/os-release) main" | tee
/etc/apt/sources.list.d/adoptium.list \
- && apt-get update \
- && apt-get -y dist-upgrade \
- && apt-get -y install temurin-${JDK_MAJOR_VERSION:-17}-jdk \
- && export ARCH=$(uname -m | sed -r 's/aarch64/arm64/g' | awk
'!/arm64/{$0="amd64"}1') \
- && echo networkaddress.cache.ttl=1 >>
/usr/lib/jvm/temurin-${JDK_MAJOR_VERSION:-17}-jdk-$ARCH/conf/security/java.security
\
- && echo networkaddress.cache.negative.ttl=1 >>
/usr/lib/jvm/temurin-${JDK_MAJOR_VERSION:-17}-jdk-$ARCH/conf/security/java.security
\
-
-# Cleanup apt
-RUN apt-get -y --purge autoremove \
- && apt-get autoclean \
- && apt-get clean \
- && rm -rf /var/lib/apt/lists/*
-
-RUN pip3 install pyyaml==6.0.1
-
-# Pulsar currently writes to the below directories, assuming the default
configuration.
-# Note that number 4 is the reason that pulsar components need write access to
the /pulsar directory.
-# 1. /pulsar/data - both bookkeepers and zookeepers use this directory
-# 2. /pulsar/logs - function workers write to this directory and pulsar-admin
initializes this directory
-# 3. /pulsar/download - functions write to this directory
-# 4. /pulsar - hadoop writes to this directory
-RUN mkdir /pulsar && chmod g+w /pulsar
+RUN apk add --no-cache \
+ bash \
+ python3 \
+ py3-pip \
+ ca-certificates
+
+RUN wget -O /etc/apk/keys/amazoncorretto.rsa.pub
https://apk.corretto.aws/amazoncorretto.rsa.pub && \
Review Comment:
Actually, I switched it to use multi-stage. It makes it more concise as
there's no need to worry about cleaning up the temporary files.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
